Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to numerical definitions or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     joaat
    -0.71
     officers
    -0.64
    styleUrls
    -0.63
     Telerik
    -0.63
    たまた
    -0.61
    ity
    -0.61
     Edg
    -0.61
     Ayu
    -0.60
    omi
    -0.60
    Steg
    -0.59
    POSITIVE LOGITS
     للمعارف
    0.99
    ']?>
    0.88
    })*/
    0.85
    Vidite
    0.84
     تانيه
    0.82
    -------------</
    0.81
    "}")
    0.80
    }))
    0.79
    ]=="
    0.79
     متعلقه
    0.77
    Act Density 0.358%

    No Known Activations